85 citations · 132 across the 9 of their papers we have counts for
9 papers
Multiple Realizability and the Rise of Deep Learning
Sam Whitman McGrath, Jacob Russin
The multiple realizability thesis holds that psychological states may be implemented in a diversity of physical systems. The deep learning revolution seems to be bringing this poss…
From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks
Jacob Russin, Sam Whitman McGrath, Danielle J. Williams
Compositionality has long been considered a key explanatory property underlying human intelligence: arbitrary concepts can be composed into novel complex combinations, permitting t…
The Relational Bottleneck as an Inductive Bias for Efficient Abstraction
Taylor W. Webb, Steven M. Frankland, Awni Altabaa +9
A central challenge for cognitive science is to explain how abstract concepts are acquired from limited experience. This has often been framed in terms of a dichotomy between conne…
A Neural Network Model of Continual Learning with Cognitive Control
Jacob Russin, Maryam Zolfaghar, Seongmin A. Park +2
Neural networks struggle in continual learning settings from catastrophic forgetting: when trials are blocked, new learning can overwrite the learning from previous blocks. Humans…
The Structure of Systematicity in the Brain
Randall C. O'Reilly, Charan Ranganath, Jacob L. Russin
A hallmark of human intelligence is the ability to adapt to new situations, by applying learned rules to new content (systematicity) and thereby enabling an open-ended number of in…
Compositional Processing Emerges in Neural Networks Solving Math Problems
Jacob Russin, Roland Fernandez, Hamid Palangi +4
A longstanding question in cognitive science concerns the learning mechanisms underlying compositionality in human cognition. Humans can infer the structured relationships (e.g., g…
Complementary Structure-Learning Neural Networks for Relational Reasoning
Jacob Russin, Maryam Zolfaghar, Seongmin A. Park +2
The neural mechanisms supporting flexible relational inferences, especially in novel situations, are a major focus of current research. In the complementary learning systems framew…
Deep Predictive Learning in Neocortex and Pulvinar
Randall C. O'Reilly, Jacob L. Russin, Maryam Zolfaghar +1
How do humans learn from raw sensory experience? Throughout life, but most obviously in infancy, we learn without explicit instruction. We propose a detailed biological mechanism f…
Compositional generalization in a deep seq2seq model by separating syntax and semantics
Jake Russin, Jason Jo, Randall C. O'Reilly +1
Standard methods in deep learning for natural language processing fail to capture the compositional structure of human language that allows for systematic generalization outside of…